crucible
v0.1.0Hard gates for the scientific method — pre-registration lock, computed sample-size, and a blind independent judge, enforced as gates the study pipeline refuses to pass. The deterministic core enforces the gates on any harness; on Codex the extra PreToolUse/Stop hooks degrade to advisory.
By nagisanzeninLicense: MIT0 GitHub starsUpdated 3 months ago
Directory evidence
- Runtimes
- Codex and Claude Code
- Parsed components
- 1 skill or MCP entry
- Source updated
- Jul 9, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install crucible for Codex and Claude Code
codex plugin marketplace add nagisanzenin/crucible
codex plugin marketplace upgrade crucible
codex plugin add crucible@cruciblePaste and run these commands in a terminal with Codex. They add and refresh the crucible catalog, then install this plugin.
Compatibility: the page URL and API slug “crucible-3” remain stable.
- Codex:
crucible-3@agent-plugin-marketplace→crucible@crucible
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/nagisanzenin/crucibleClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.
Plugin files
├── .codex-plugin/plugin.json├── .claude-plugin/plugin.json└── skills/crucible/SKILL.md
Included Skills1
Run a scientific study that is actually SOLID — pre-registered, adequately powered, and blind-judged — so the conclusion is defensible and whatever you build on top of it isn't built on sand. Use when the user wants to run an experiment, A/B test, ablation, eval, or comparison and have the result HOLD UP. crucible enforces the three disciplines an agent skips (pre-registration, sample size, blind judging) as gates the pipeline refuses to pass.
Plugin manifests2
{
"name": "crucible",
"version": "0.1.0",
"description": "Hard gates for the scientific method — pre-registration lock, computed sample-size, and a blind independent judge, enforced as gates the study pipeline refuses to pass. The deterministic core enforces the gates on any harness; on Codex the extra PreToolUse/Stop hooks degrade to advisory.",
"author": {
"name": "nagisanzenin"
},
"homepage": "https://github.com/nagisanzenin/crucible",
"keywords": [
"scientific-method",
"rigor",
"pre-registration",
"experiment",
"evaluation",
"ab-test",
"statistics",
"blind-judge",
"reproducibility",
"research"
],
"skills": "./skills/",
"hooks": "./hooks/hooks.json",
"interface": {
"displayName": "Crucible",
"category": "research"
}
}{
"name": "crucible",
"version": "0.1.0",
"description": "Hard gates for the scientific method — so an AI agent can't ship a study that fools itself. Pre-registration lock, computed sample-size, and a blind independent judge, enforced as gates the pipeline refuses to pass.",
"author": {
"name": "nagisanzenin"
},
"homepage": "https://github.com/nagisanzenin/crucible",
"keywords": [
"scientific-method",
"rigor",
"pre-registration",
"experiment",
"evaluation",
"ab-test",
"statistics",
"blind-judge",
"reproducibility",
"research"
],
"license": "MIT"
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[crucible on Agent Plugins Marketplace](https://pluginsmp.com/plugins/crucible-3)